Search papers, labs, and topics across Lattice.
2
0
4
11
Scaling visuomotor context to 8K timesteps enables robots to master complex tasks and adapt in real-time, outperforming previous models by a staggering margin.
Forget synthetic data鈥攕caling up human egocentric video by 20x unlocks surprisingly effective dexterous robot manipulation, even transferring to robots with different hand configurations.
